Skip to main content
Glama

Ellimist

Check a queued or confirming purchase (free)

get_task
Read-only

Poll a task returned by a paid tool: pass its task_id and the read_token from the task's access block. Returns its state and, once complete, the signed result. Free.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task_id": "<task_id>",
      "read_token": "<read_token>"
    },
    "name": "get_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
task_idYes
read_tokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered by structured data. The description adds genuinely useful behavior context: the read_token must come from "the task's access block" (an auth requirement) and the result only appears "once complete." However, it says nothing about task lifetime, token expiry, or how long a signed result remains retrievable, which matters for a polling loop.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences and one fragment, with the action and the parameter sourcing front-loaded before the return values and the "Free." note. No sentence restates the name or wastes space.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter polling tool with no output schema, the description must describe returns, and it does say "state and, once complete, the signed result." But it never enumerates the possible states (queued, confirming, complete, failed) or the error shapes an agent will need to branch on, leaving a notable gap for the tool's core polling use case.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for both parameters and it does add real meaning: read_token is sourced from "the task's access block" and task_id identifies a task produced by a paid tool. It still leaves gaps, such as what happens with an expired or mismatched read_token, but it supplies the essential provenance the schema lacks; the minimum-viable baseline applies rather than a higher score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

It names a specific verb ("Poll") and a specific resource ("a task returned by a paid tool"), and states what comes back (state and, once complete, the signed result). It implicitly separates itself from cancel_task by being a read/poll operation, but never names or contrasts a sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase "poll a task returned by a paid tool" tells the agent exactly the situation in which this tool applies, and "Free" signals that repeated polling carries no cost. It stops short of when-not guidance: no polling cadence, no advice on how long to keep polling, and no mention of when to give up and use cancel_task.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources